Lights: Light Specularity Dataset For Specular Detection In Multi-View

Specular highlights are commonplace in images, however, methods for detecting them and removing the phenomenon are particularly challenging. A reason for this is the difficulty in creating a dataset for training or evaluation, as in the real world, we lack the necessary control over the environment....

Full description

Saved in:
Bibliographic Details
Published in2021 IEEE International Conference on Image Processing (ICIP) pp. 2908 - 2912
Main Authors Elkhouly, Mohamed Dahy, Tsesmelis, Theodore, Bue, Alessio Del, James, Stuart
Format Conference Proceeding
LanguageEnglish
Published IEEE 19.09.2021
Subjects
Conferences
Dataset
Face-based specular detection
Faces
Image processing
Lighting
Multi-view
Specular-highlights
Task analysis
Training
Transportation
Online AccessGet full text

Cover

More Information
Summary:Specular highlights are commonplace in images, however, methods for detecting them and removing the phenomenon are particularly challenging. A reason for this is the difficulty in creating a dataset for training or evaluation, as in the real world, we lack the necessary control over the environment. Therefore, we propose a novel physically-based rendered LIGHT Specularity (LIGHTS) Dataset for the evaluation of the specular highlight detection task. Our dataset consists of 18 high-quality architectural scenes, where each scene is rendered with multiple views. In total, the dataset contains 2, 603 views with an average of 145 views per scene. Additionally, we propose a simple aggregation based method for specular highlight detection that outperforms prior work by 3.6% in two orders of magnitude less time on our dataset.
ISSN:2381-8549
DOI:10.1109/ICIP42928.2021.9506354